InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models

• URL: http://arxiv.org/abs/2607.07288v1
• Date: Wed, 08 Jul 2026 11:28:15 GMT
• Title: InfraQR: Edge-Placed QR-Inspired Structured Patch Attacks on Infrared Vision-Language Models
• Abstract summary: We present InfraQR, a QR-inspired structured patch attack for infrared vision-language models.<n>We evaluate it on infrared classification, caption transfer, and question-answer-aware visual question answering tasks.<n>Results show that infrared vision-language models remain vulnerable to structured edge-placed perturbations.
• Score: 6.982777059279356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Infrared vision-language models are increasingly used for perception under low-light and adverse visual conditions, yet their robustness to localized structured perturbations remains underexplored. Existing infrared adversarial studies mainly focus on object detectors, leaving the security of infrared vision-language models less systematically examined. We present InfraQR, a QR-inspired structured patch attack for infrared vision-language models. Unlike localized attacks that attach perturbations to the target object, InfraQR places a compact structured patch along image boundaries and optimizes learnable grid cells through surrogate CLIP-style encoders. The resulting patch has a near-binary structured appearance, but is not required to be a valid or machine-readable QR code. We evaluate InfraQR on infrared classification, caption transfer, and question-answer-aware visual question answering (VQA) tasks. On a 300-image infrared benchmark, InfraQR sharply reduces the accuracy of multiple CLIP-style classifiers, including reducing OpenAI CLIP accuracy from 98.67% to 0.70%. The generated adversarial images also transfer to black-box captioning and VQA models, causing semantic degradation in captions and more error-prone answers under GPT-5.4-based evaluation. These results show that infrared vision-language models remain vulnerable to structured edge-placed perturbations, motivating further study of cross-task robustness beyond direct object occlusion.

Related papers

• InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models [9.310612317083928]
  Infrared vision-adaptive models (IR-VLMs) have emerged as a promising paradigm for multimodal perception under low-visibility conditions.<n>We propose InfraPatch, a framework for targeted digital grayscale patch attacks against IR-VLMs.
  arXiv  Detail & Related papers  (2026-09-02T07:42:27Z)
• SC-Diff: Semantically Calibrated Diffusion for Visible-to-Infrared Image Translation [52.62632888060867]
  Visible-to-infrared image translation provides a practical way to expand infrared training data using abundant visible images.<n>Existing diffusion-based methods typically use semantic priors only as external conditions.<n>We propose SC-Diff, a semantically latent diffusion framework that uses semantic priors for both conditional guidance and internal self-attention calibration.
  arXiv  Detail & Related papers  (2026-08-09T07:57:40Z)
• FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity [50.75932774177958]
  FaithIR is a faithful infrared super-resolution framework for reliable machine perception.<n>Experiments on FLIR-IISR, M3FD, and FMB demonstrate strong reconstruction fidelity, cross-dataset generalization, and superior performance in object detection and semantic segmentation.
  arXiv  Detail & Related papers  (2026-08-04T04:23:30Z)
• QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models [15.94973805868716]
  Infrared vision-language models (IR-VLMs) extend thermal perception to open-vocabulary classification, image captioning, and visual question answering.<n>We propose QR-Structured Thermal Triggers (QR-STT), a framework for targeted semantic steering of IR-VLMs.<n>We show that QR-STT consistently redirects image-text alignment toward chosen concepts while maintaining visual stealth.
  arXiv  Detail & Related papers  (2026-07-31T14:10:57Z)
• MonoIR-RS: Infrared Remote Sensing Vision-Language Learning with CLIP and VLM Adaptation [12.037405766509274]
  MonoIR-RS is a large-scale infrared remote-sensing vision-language dataset.<n>It couples IR-aware data construction with CLIP-style contrastive adaptation and VLM instruction tuning.<n>We show that the synthesized infrared imagery is markedly closer to real thermal imagery than a grayscale conversion.
  arXiv  Detail & Related papers  (2026-07-07T17:53:58Z)
• Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling [49.887347082863194]
  We show that relative thermal radiation relations between different classes can be regarded as a reliable knowledge source under the complex scenarios of adversarial examples and common corruptions.<n>We propose Knowledge-Guided Adversarial Training (KGAT) for infrared object detection, in which infrared physical knowledge is embedded into the adversarial training process.
  arXiv  Detail & Related papers  (2026-03-26T08:43:43Z)
• Vision-Language Models for Infrared Industrial Sensing in Additive Manufacturing Scene Description [1.7786984823452563]
  Infrared cameras provide advantages in manufacturing environments in low-light conditions or enclosed machines where vision systems struggle.<n>Recent advances in vision-language systems (VLMs) offer new in-text predictions in relation to RGB data.<n>This work introduces a zero-shot encoder that adapts VLMs to infrared data by preprocessing images captured by a FLIR Boson camera.
  arXiv  Detail & Related papers  (2025-12-11T20:20:38Z)
• DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance [20.484726951373602]
  In this paper, we propose a Dual-domain Guided Infrared foundation model based on MAE (DuGI-MAE)<n>First, we design a deterministic masking strategy based on token entropy, preserving only high-entropy tokens for reconstruction to enhance informativeness.<n>Next, we introduce a Dual-Domain Guidance (DDG) module, which simultaneously captures global token relationships and adaptively filters non-uniform background noise commonly present in infrared imagery.<n>Pretrained on Inf-590K, DuGI-MAE demonstrates strong generalization capabilities across various downstream tasks, including infrared object detection, semantic segmentation, and small target detection
  arXiv  Detail & Related papers  (2025-12-04T06:45:20Z)
• IrisNet: Infrared Image Status Awareness Meta Decoder for Infrared Small Targets Detection [92.56025546608699]
  IrisNet is a novel meta-learned framework that adapts detection strategies to the input infrared image status.<n>Our approach establishes a dynamic mapping between infrared image features and entire decoder parameters.<n> Experiments on NUDT-SIRST, NUAA-SIRST, and IRSTD-1K datasets demonstrate the superiority of our IrisNet.
  arXiv  Detail & Related papers  (2025-11-25T13:53:54Z)
• DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing [55.366556355538954]
  We propose the Dynamic Iterative Shrinkage Thresholding Network (DISTA-Net), which reconceptualizes traditional sparse reconstruction within a dynamic framework.<n>DISTA-Net is the first deep learning model designed specifically for the unmixing of closely-spaced infrared small targets.<n>We have established the first open-source ecosystem to foster further research in this field.
  arXiv  Detail & Related papers  (2025-05-25T13:52:00Z)
• SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems [1.891522135443594]
  Domain-adaptive thermal object detection plays a key role in facilitating visible (RGB)-to-thermal (IR) adaptation.<n>In inherent limitations of IR images, such as the lack of color and texture cues, pose challenges for RGB-trained models.<n>We propose Semantic-Aware Gray color Augmentation (SAGA), a novel strategy for mitigating color bias and bridging the domain gap.
  arXiv  Detail & Related papers  (2025-04-22T09:22:11Z)
• Multi-Domain Biometric Recognition using Body Embeddings [51.36007967653781]
  We show that body embeddings perform better than face embeddings in medium-wave infrared (MWIR) and long-wave infrared (LWIR) domains.<n>We leverage a vision transformer architecture to establish benchmark results on the IJB-MDF dataset.<n>We also show that finetuning a body model, pretrained exclusively on VIS data, with a simple combination of cross-entropy and triplet losses achieves state-of-the-art mAP scores.
  arXiv  Detail & Related papers  (2025-03-13T22:38:18Z)
• Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution [54.293362972473595]
  Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts. Current approaches to address SR tasks are either dedicated to extracting RGB image features or assuming similar degradation patterns. We propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
  arXiv  Detail & Related papers  (2024-11-19T14:24:03Z)
• Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds [155.388487263872]
  We propose a new infrared small-dim target detection method with the transformer. We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range. We also design a feature enhancement module to learn more features of small-dim targets.
  arXiv  Detail & Related papers  (2021-09-29T12:23:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.